Large Language Models: How Large is Large Enough?

[@dominiquecoladon8343]

Well done video, Get kip to more of these please.

[@worldwar_two2894]

excellent insight! luv this! Kip, keep it up! 🎊🎊

[@MrTehRave]

Video clean as hell. Great stuff

[@thatdudewiththething]

These videos are fantastic! Thank you so much for making them available :D

[@ttjordan81]

Thank you, this is the information I was searching for. I was explaining the concept in theory to someone. The idea was to use smaller models that are trained for specific domains. By eliminating or reduce all the other domains, the model should perform better and reduce messy results.

[@LaurenFrazier-ch4kn]

Great video, super informative!

[@YvesNewman]

Great video Kip! At the moment it seems that bigger equals better. Time to change that perception accordingly

[@sherpya]

already the trend, see mixture of experts concept

[@IsaacFoster..]

My llm's so large, it reaches almost every 1 and 0 it can write on; you can literally call it a "wipe"

[@gjjakobsen]

The MBA in me says, beyond some point, the trade-off isn't worth it. Then again, that's probably what they said about the Apollo mission.

[@donson3326]

0:16 🤣 You tell me.

[@di-egohumilde4515]

I had EXACTLY the same thought LMAO

[@7rich79]

Thank you, that was informative. One question I have is how you determine domain specificity, and perhaps potential lost opportunity? For example, using financial services tasks as in your example. If you ask someone working in finance about what insights they'd be looking for, tax or perhaps transfer pricing may not be what they consider as part of their domain. However, transfer pricing and tax could have a huge impact on what finance should consider when taking decisions. How do you ensure the domain specificity is not too narrow?

[@julioberas2106]

I believe anything remotely related to the domains should be included in the training data. He didn't talk about the training data size, but I believe it should still be very big (but smaller than a general one)

[@Alice8000]

5:38 THANK YOU BRO. Definitely feel more confident after hearing that.

[@nirmal7103]

How can we find a domain specific models or how to train them?

[@ttjordan81]

I think that's the next business idea, lol... At this point, pick an industry, and create specific domain model! It's a race! Also, specific domain Vector Databases will be needed!

[@einstein_god]

It really depends

[@tyrojames9937]

INTERESTING. 😀

[@aberobwohl]

I see no point whatsoever in comparing a domain specific finetuned model to a non finetuned model to draw conclusions or suggest any insights doing this.

[@warsin8641]

The Bloke

[@deathlife2414]

Lets go phi. chroot chroot chroot

[@Alice8000]

bro you got worse handwriting than me!!! Good info though. lol

[@TheBiffsterLife]

Kip, that’s a very poor analogy.